• Dropbox Dash uses AI to understand questions about your files, work chats, and company content, bringing everything together in one place for deeper, more focused work. • With tens of thousands of potential work documents to consider, both search and agents rely on a ranking system powered by real-time machine learning to find the right files fast. • At the core of that ranking in Dash is our feature store, a system that manages and delivers the data signals (“features”) our models use to predict relevance. • To help users find exactly what they need, Dash has to read between the lines of user behavior across file types, company content, and the messy, fragmented realities of collaboration. • Then it has to surface the most relevant documents, images, and conversations when and how they’re needed. • The feature store is a critical part of how we rank and retrieve the right context across your work.
Article Summaries:
- Dropbox has built a custom feature store to power the real‑time AI ranking engine in its Dash workspace assistant. Dash uses machine‑learning models to surface relevant files, images, and conversations across a company’s fragmented data. Because the system must serve thousands of feature lookups per query with sub‑100 ms latency, Dropbox’s hybrid on‑premises and Spark‑native cloud infrastructure made off‑the‑shelf feature stores unsuitable. The team surveyed options such as Feast, Hopsworks, and Tecton, ultimately adopting Feast’s architecture but extending it to support both real‑time streaming and batch‑processed features. The result is a high‑speed, scalable store that ingests user signals within seconds and keeps relevance models fresh as behavior changes.
Sources: